INDEX

Explanations

references to sections and subsections in a document

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BagLayout

-0.95

AsUp

-0.79

🏻

-0.78

Vem

-0.77

DockStyle

-0.75

velopes

-0.74

 Arquite

-0.74

__*/

-0.74

IsPostBack

-0.74

 mouseY

-0.73

POSITIVE LOGITS

 section

1.71

 Section

1.62

 sections

1.58

Section

1.53

 Sections

1.53

SECTION

1.52

 SECTION

1.52

Sections

1.47

 SECTIONS

1.36

section

1.32

Activations Density 0.168%

references to sections and subsections in a document

No Comments

No Known Activations